do
/do - Manifest Executor
Goal
Execute a Manifest: satisfy all Deliverables' Acceptance Criteria while following Process Guidance and using Approach as initial direction (adapting when reality diverges), then verify everything passes (including Global Invariants).
Why quality execution matters: The manifest front-loaded the thinking—criteria are already defined. Your job is implementation that passes verification on first attempt. Every verification failure is rework.
Input
$ARGUMENTS = manifest file path (REQUIRED), optionally with execution log path and --mode <level>
If no arguments: Output error "Usage: /do [log-file-path] [--mode efficient|balanced|thorough]"
Execution Mode
Resolve mode from (highest precedence first): --mode argument → manifest mode: field → default thorough.
Invalid mode value → error and halt: "Invalid mode ''. Valid modes: efficient | balanced | thorough"
More from doodledood/manifest-dev
define
Manifest builder. Plan work, scope tasks, spec out requirements, break down complex tasks before implementation. Converts needs into Deliverables + Invariants with verification criteria. Use when planning features, debugging complex issues, scoping refactors, or whenever a task needs structured thinking before coding.
15review-prompt
Review and analyze LLM prompts against prompt-engineering principles. Provides detailed assessment without modifying files.
1auto-optimize-prompt
Iteratively auto-optimize a prompt until no issues remain. Uses prompt-reviewer in a loop, asks user for ambiguities, applies fixes via prompt-engineering skill. Runs until converged.
1prompt-engineering
Craft, update, or review LLM prompts from first principles. Use when creating new prompts, updating existing ones, reviewing prompt structure, or diagnosing a failing prompt. Ensures prompts define WHAT and WHY, not HOW. Triggers: write a prompt, edit a prompt, review a prompt, improve a prompt, diagnose prompt failure, fix failing prompt, system prompt, skill, agent.
1